{"id":"https://openalex.org/W4403582508","doi":"https://doi.org/10.1145/3627673.3680011","title":"Personalized Video Summarization by Multimodal Video Understanding","display_name":"Personalized Video Summarization by Multimodal Video Understanding","publication_year":2024,"publication_date":"2024-10-20","ids":{"openalex":"https://openalex.org/W4403582508","doi":"https://doi.org/10.1145/3627673.3680011"},"language":"en","primary_location":{"id":"doi:10.1145/3627673.3680011","doi":"https://doi.org/10.1145/3627673.3680011","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3627673.3680011","pdf_url":null,"source":{"id":"https://openalex.org/S4393918199","display_name":"ACM International Conference on Information and Knowledge Management (CIKM)","issn_l":"2155-0751","issn":["2155-0751"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Information and Knowledge Management","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1145/3627673.3680011","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Brian Chen","orcid":"https://orcid.org/0000-0001-9025-0107","observed_orcids":["https://orcid.org/0000-0001-9025-0107"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Brian Chen","raw_affiliation_strings":["VDIL, Samsung Research America, Irvine, CA, USA"],"raw_orcid":"https://orcid.org/0000-0001-9025-0107","affiliations":[{"raw_affiliation_string":"VDIL, Samsung Research America, Irvine, CA, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Xiangyuan Zhao","orcid":"https://orcid.org/0009-0009-8220-6347","observed_orcids":["https://orcid.org/0009-0009-8220-6347"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiangyuan Zhao","raw_affiliation_strings":["VDIL, Samsung Research America, Irvine, CA, USA"],"raw_orcid":"https://orcid.org/0009-0009-8220-6347","affiliations":[{"raw_affiliation_string":"VDIL, Samsung Research America, Irvine, CA, USA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5076910439","display_name":"Yingnan Zhu","orcid":"https://orcid.org/0009-0000-5709-1335","observed_orcids":["https://orcid.org/0009-0000-5709-1335"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yingnan Zhu","raw_affiliation_strings":["VDIL, Samsung Research America, irvine, CA, USA"],"raw_orcid":"https://orcid.org/0009-0000-5709-1335","affiliations":[{"raw_affiliation_string":"VDIL, Samsung Research America, irvine, CA, USA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.4498,"has_fulltext":true,"cited_by_count":7,"citation_normalized_percentile":{"value":0.87730173,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"4382","last_page":"4389"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11439","display_name":"Video Analysis and Summarization","score":0.9990000128746033,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11439","display_name":"Video Analysis and Summarization","score":0.9990000128746033,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.0005000000237487257,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12720","display_name":"Multimedia Communication and Technology","score":0.0,"subfield":{"id":"https://openalex.org/subfields/3312","display_name":"Sociology and Political Science"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/user-preferences","display_name":"user preferences","score":0.6690000295639038},{"id":"https://openalex.org/keywords/vision-language-models","display_name":"vision-language models","score":0.9359999895095825},{"id":"https://openalex.org/keywords/closed-captioning","display_name":"closed captioning","score":0.8040000200271606},{"id":"https://openalex.org/keywords/genre-preferences","display_name":"genre preferences","score":0.8349999785423279},{"id":"https://openalex.org/keywords/unsupervised-video-summarization","display_name":"unsupervised video summarization","score":0.9760000109672546},{"id":"https://openalex.org/keywords/multimodal-video-understanding","display_name":"multimodal video understanding","score":0.7319999933242798}],"concepts":[{"id":"https://openalex.org/C170858558","wikidata":"https://www.wikidata.org/wiki/Q1394144","display_name":"Automatic summarization","level":2,"score":0.9318559169769287},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7805507779121399},{"id":"https://openalex.org/C65483669","wikidata":"https://www.wikidata.org/wiki/Q3536669","display_name":"Video processing","level":2,"score":0.4487713873386383},{"id":"https://openalex.org/C117090137","wikidata":"https://www.wikidata.org/wiki/Q7927977","display_name":"Video post-processing","level":5,"score":0.4376852512359619},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.42679351568222046},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4052906036376953},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.39506763219833374},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3443988561630249},{"id":"https://openalex.org/C23431618","wikidata":"https://www.wikidata.org/wiki/Q1404672","display_name":"Multiview Video Coding","level":4,"score":0.2997077405452728}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/3627673.3680011","doi":"https://doi.org/10.1145/3627673.3680011","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3627673.3680011","pdf_url":null,"source":{"id":"https://openalex.org/S4393918199","display_name":"ACM International Conference on Information and Knowledge Management (CIKM)","issn_l":"2155-0751","issn":["2155-0751"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Information and Knowledge Management","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2411.03531","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2411.03531","pdf_url":"https://arxiv.org/pdf/2411.03531","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2411.03531","doi":"https://doi.org/10.48550/arxiv.2411.03531","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2411.03531","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article-journal"}],"best_oa_location":{"id":"doi:10.1145/3627673.3680011","doi":"https://doi.org/10.1145/3627673.3680011","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3627673.3680011","pdf_url":null,"source":{"id":"https://openalex.org/S4393918199","display_name":"ACM International Conference on Information and Knowledge Management (CIKM)","issn_l":"2155-0751","issn":["2155-0751"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Information and Knowledge Management","raw_type":"proceedings-article"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W52770770","https://openalex.org/W2529272619","https://openalex.org/W2610416447","https://openalex.org/W2737677090","https://openalex.org/W2963508075","https://openalex.org/W2981852735","https://openalex.org/W2996811227","https://openalex.org/W3016201367","https://openalex.org/W3033386097","https://openalex.org/W3099156605","https://openalex.org/W3126245673","https://openalex.org/W3214448253","https://openalex.org/W4234552385","https://openalex.org/W4283363598","https://openalex.org/W4285606530","https://openalex.org/W4312748990","https://openalex.org/W4319300292","https://openalex.org/W4386083094","https://openalex.org/W4390873341"],"related_works":["https://openalex.org/W2031428098","https://openalex.org/W2166885850","https://openalex.org/W2177318691","https://openalex.org/W4372048963","https://openalex.org/W2005651667","https://openalex.org/W7166550068","https://openalex.org/W4398223129","https://openalex.org/W4417356735","https://openalex.org/W3197682865","https://openalex.org/W2105442915"],"abstract_inverted_index":{"Video":[0,98],"summarization":[1,28,58,86,106,124,184,202],"techniques":[2],"have":[3],"been":[4],"proven":[5],"to":[6,15,59,116,120,198],"improve":[7],"the":[8,22,44,53,118,146,156,163,167,205,207,223],"overall":[9],"user":[10,65,90,226],"experience":[11],"when":[12,220],"it":[13],"comes":[14],"accessing":[16],"and":[17,64,71,136,141,228],"comprehending":[18],"video":[19,27,57,63,85,105,123,135,151,183,201],"content.":[20],"If":[21],"user's":[23,157],"preference":[24,159],"is":[25,108,191,214],"known,":[26],"can":[29],"identify":[30],"significant":[31,68],"information":[32,46],"or":[33,47],"relevant":[34],"content":[35],"from":[36],"an":[37],"input":[38,140],"video,":[39],"aiding":[40],"them":[41],"in":[42,51],"obtaining":[43],"necessary":[45],"determining":[48],"their":[49],"interest":[50],"watching":[52],"original":[54],"video.":[55],"Adapting":[56],"various":[60,89],"types":[61],"of":[62,225],"preferences":[66,227],"requires":[67],"training":[69,129],"data":[70],"expensive":[72],"human":[73],"labeling.":[74],"To":[75],"facilitate":[76],"such":[77],"research,":[78],"we":[79,93],"proposed":[80,177],"a":[81,95,122,127],"new":[82],"benchmark":[83],"for":[84,103,165,217],"that":[87,107,175,188,211],"captures":[88],"preferences.":[91],"Also,":[92],"present":[94],"pipeline":[96,132,178,213],"called":[97],"Summarization":[99],"with":[100],"Language":[101],"(VSL)":[102],"user-preferred":[104],"based":[109],"on":[110,126],"pre-trained":[111],"visual":[112],"language":[113],"models":[114],"(VLMs)":[115],"avoid":[117],"need":[119],"train":[121],"system":[125],"large":[128],"dataset.":[130],"The":[131,171],"takes":[133],"both":[134],"closed":[137],"captioning":[138],"as":[139,162],"performs":[142],"semantic":[143],"analysis":[144,209],"at":[145],"scene":[147],"level":[148],"by":[149],"converting":[150],"frames":[152],"into":[153],"text.":[154],"Subsequently,":[155],"genre":[158],"was":[160],"used":[161],"basis":[164],"selecting":[166],"pertinent":[168],"textual":[169],"scenes.":[170],"experimental":[172],"results":[173],"demonstrate":[174],"our":[176,189,212],"outperforms":[179],"current":[180],"state-of-the-art":[181],"unsupervised":[182],"models.":[185,203],"We":[186],"show":[187],"method":[190],"more":[192,215],"adaptable":[193],"across":[194],"different":[195],"datasets":[196],"compared":[197],"supervised":[199],"query-based":[200],"In":[204],"end,":[206],"runtime":[208],"demonstrates":[210],"suitable":[216],"practical":[218],"use":[219],"scaling":[221],"up":[222],"number":[224],"videos.":[229]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":2}],"updated_date":"2026-10-26T11:51:55.731654","created_date":"2024-10-21T00:00:00"}